INDEX

Explanations

expressions indicating a strong level of certainty or emphasis

oai_token-act-pair · gpt-3.5-turbo

statements or phrases expressing certainty or confirmation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

idas

-0.81

awaru

-0.81

entary

-0.79

ingly

-0.77

gencies

-0.71

ULAR

-0.69

agus

-0.69

ENCY

-0.66

ilaterally

-0.66

 respectively

-0.65

POSITIVE LOGITS

 qualifies

0.78

 deserved

0.77

 wasn

0.68

 suited

0.67

 weren

0.67

 influenced

0.67

 ought

0.67

 enjoyed

0.66

 wouldn

0.66

 benefited

0.66

Activations Density 0.036%

expressions indicating a strong level of certainty or emphasis

statements or phrases expressing certainty or confirmation

No Comments

No Known Activations