INDEX

Explanations

terms related to continuous processes or functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Theſe

-1.19

 pleaſure

-1.14

RenderAtEndOf

-1.14

 Shakspeare

-1.13

 becauſe

-1.11

 Anſ

-1.09

 leaſt

-1.07

 ſind

-1.06

 ſche

-1.06

 myſelf

-1.05

POSITIVE LOGITS

0.77

<eos>

0.75

0.68

non

0.64

 development

0.62

↵↵

0.60

<sup>

0.60

 information

0.60

 rest

0.59

and

0.59

Activations Density 0.184%

terms related to continuous processes or functions

No Comments

No Known Activations