INDEX

Explanations

phrases related to political figures and discussions

oai_token-act-pair · gpt-3.5-turbo

references to specific organizations or entities, particularly in a political or policy context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DragonMagazine

-0.86

kefeller

-0.79

xit

-0.77

issance

-0.77

osaurus

-0.74

apore

-0.73

utenant

-0.70

theless

-0.70

pire

-0.69

icken

-0.68

POSITIVE LOGITS

 Gamble

0.61

INTER

0.53

 melan

0.53

 Full

0.52

 Roof

0.52

 aspirin

0.51

Rew

0.51

 puff

0.50

 Blind

0.49

 Enough

0.48

Activations Density 0.172%

phrases related to political figures and discussions

references to specific organizations or entities, particularly in a political or policy context

No Comments

No Known Activations