INDEX

Explanations

timestamps and post identifiers

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

SharedDtor

-0.57

 américains

-0.56

argout

-0.55

TEMPLATES

-0.54

premi

-0.53

Източници

-0.52

>",

-0.52

 picioare

-0.52

 Stolz

-0.51

hotra

-0.51

POSITIVE LOGITS

 AssemblyTitle

0.61

complexContent

0.59

 Maradona

0.59

новништво

0.57

tvguidetime

0.56

setopt

0.55

 snippetHide

0.52

 UIAlert

0.51

 marvellous

0.51

 mobilisation

0.49

Activations Density 0.084%

timestamps and post identifiers

No Comments

No Known Activations