INDEX

Explanations

mentions of corrupt individuals or practices

oai_token-act-pair · gpt-3.5-turbo

mentions of 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ciation

-0.84

gain

-0.74

ILA

-0.71

ãĥ¼ãĥ³

-0.71

ynthesis

-0.69

WAYS

-0.68

UNCH

-0.67

yip

-0.67

gat

-0.67

planes

-0.66

POSITIVE LOGITS

ly

0.91

 corrupt

0.84

ingly

0.84

nesses

0.81

ions

0.77

ible

0.76

ulent

0.75

 overse

0.74

 mole

0.74

 undermin

0.71

Activations Density 0.036%

mentions of corrupt individuals or practices

mentions of corruption in various contexts

No Comments

No Known Activations