INDEX

Explanations

mentions of corrupt practices or individuals

oai_token-act-pair · gpt-3.5-turbo

references to corruption in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ynthesis

-0.76

gain

-0.73

WAYS

-0.72

 Anxiety

-0.72

ãĥ¼ãĥ³

-0.71

UNCH

-0.71

gat

-0.71

ruck

-0.69

ankind

-0.69

TRY

-0.66

POSITIVE LOGITS

 corrupt

0.89

ible

0.85

ions

0.85

ly

0.83

ingly

0.80

ulent

0.79

 dealings

0.77

ibly

0.72

 undermin

0.72

iated

0.71

Activations Density 0.026%

mentions of corrupt practices or individuals

references to corruption in various contexts

No Comments

No Known Activations