INDEX

Explanations

occurrences of the "&" symbol indicating connections or conjunctions in contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

-0.62

 bowiem

-0.59

-0.56

-0.55

blockSize

-0.55

-0.54

 Wiktionnaire

-0.54

principalTable

-0.54

FormBuilder

-0.54

üle

-0.51

POSITIVE LOGITS

amp

2.12

ndash

1.60

quot

1.52

mdash

1.39

ldquo

1.31

httphttps

1.12

raquo

1.10

middot

1.04

nbsp

1.04

hellip

1.03

Activations Density 0.053%

occurrences of the "&" symbol indicating connections or conjunctions in contexts

No Comments

No Known Activations