INDEX

Explanations

references to specific activities or actions involving objects

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kontinu

-1.05

 kompati

-0.98

 Mémoires

-0.96

 chande

-0.95

 tremb

-0.95

 silikon

-0.94

 protokol

-0.93

 plis

-0.92

 akut

-0.90

 pecuni

-0.89

POSITIVE LOGITS

 entire

0.71

 rest

0.63

Wichtig

0.63

Inne

0.63

Pozdrawiam

0.60

 whole

0.60

 same

0.59

Glej

0.58

Sklici

0.58

 latter

0.57

Activations Density 0.482%

references to specific activities or actions involving objects

No Comments

No Known Activations