INDEX

Explanations

methods related to retrieving and manipulating object attributes or states

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

-0.69

-0.63

-0.62

-0.61

set

-0.60

-0.59

se

-0.59

//

-0.59

POSITIVE LOGITS

 myſelf

1.62

 himſelf

1.52

ſelf

1.50

 itſelf

1.49

 themſelves

1.46

ſelves

1.42

 pleaſure

1.36

 purpoſe

1.32

 raiſ

1.28

 ſever

1.25

Activations Density 0.036%

methods related to retrieving and manipulating object attributes or states

No Comments

No Known Activations