INDEX

Explanations

references to "function" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Jefus

-0.97

 myſelf

-0.95

 faſt

-0.94

 ſtate

-0.93

 Majefty

-0.92

 themſelves

-0.90

 ſmall

-0.90

 chré

-0.90

 poffible

-0.89

 juſt

-0.87

POSITIVE LOGITS

 function

2.34

 functions

2.31

 Function

2.21

functions

2.13

Function

2.07

 Functions

2.03

function

2.03

Functions

1.90

 FUNCTION

1.89

FUNCTION

1.87

Activations Density 0.129%

references to "function" in various contexts

No Comments

No Known Activations