INDEX

Explanations

contexts related to specific activities or hobbies that involve use of technology or creativity.

oai_token-act-pair · gpt-4o-mini Triggered by @bot

information regarding a variety of topics related to personal experiences, events, observations, and opinions.

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

phrases or expressions that categorize or describe a type or kind of thing, particularly in the format "this/these/that kind/sort of [noun]".

oai_token-act-pair · claude-3-5-sonnet-20240620 Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 odkazy

-0.50

 esternos

-0.49

multer

-0.49

ėjimo

-0.48

CppMethod

-0.45

__':

-0.45

 geholfen

-0.45

kata

-0.44

værende

-0.44

斎藤

-0.43

POSITIVE LOGITS

 kind

3.09

 type

3.06

 types

2.75

 kinds

2.74

 tipo

2.46

type

2.45

kind

2.45

 sort

2.44

 sorts

2.31

kinds

2.17

Activations Density 0.664%

contexts related to specific activities or hobbies that involve use of technology or creativity.

information regarding a variety of topics related to personal experiences, events, observations, and opinions.

phrases or expressions that categorize or describe a type or kind of thing, particularly in the format "this/these/that kind/sort of [noun]".

No Comments

No Known Activations