INDEX

Explanations

statements of ongoing actions or experiences

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

 purpoſe

-0.95

 Chriftian

-0.91

 itſelf

-0.90

ſelf

-0.88

AndEndTag

-0.88

 themſelves

-0.88

 Reſ

-0.88

 Jefus

-0.87

Efq

-0.87

 myſelf

-0.86

POSITIVE LOGITS

as

0.49

 kér

0.49

rotum

0.49

ve

0.48

ja

0.47

te

0.46

 GenerationType

0.46

 EconPapers

0.45

’

0.44

Activations Density 0.385%

statements of ongoing actions or experiences

No Comments

No Known Activations