INDEX

Explanations

mentions of names or identities in a text

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

 „,

-0.96

 inder

-0.96

 ?...

-0.93

 effe

-0.92

»>

-0.82

§.

-0.81

 desir

-0.81

 uncin

-0.81

aen

-0.79

 illi

-0.79

POSITIVE LOGITS

nor

1.33

nor

0.94

 anymore

0.90

 whatsoever

0.82

 neither

0.81

 sondern

0.80

Nor

0.78

Nor

0.75

 unless

0.74

 except

0.74

Activations Density 0.804%

mentions of names or identities in a text

No Comments

No Known Activations