INDEX

Explanations

sequences of underscores or whitespace characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.61

-0.60

vol

-0.59

-0.58

vol

-0.58

The

-0.56

mid

-0.56

-0.54

POSITIVE LOGITS

 pleaſure

1.17

 myſelf

1.08

 preſent

0.98

 ſtate

0.97

 itſelf

0.97

ⓧ

0.93

 ſhe

0.92

 ſche

0.92

+#+

0.91

 greateſt

0.91

Activations Density 0.402%

sequences of underscores or whitespace characters

No Comments

No Known Activations