INDEX

Explanations

references to recording processes or media

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rrggbb

-0.65

 متعلقه

-0.65

 '\\;'

-0.62

 ());

-0.59

nsis

-0.58

']>;

-0.57

 Held

-0.55

-};

-0.55

[];

-0.55

=?";

-0.55

POSITIVE LOGITS

 recording

1.11

 record

1.03

 Recording

1.02

recording

0.98

Recording

0.95

 RECORDING

0.90

 Record

0.83

findpost

0.82

 records

0.82

record

0.81

Activations Density 0.154%

references to recording processes or media

No Comments

No Known Activations