INDEX

Explanations

segments discussing problems, issues, or critiques

oai_token-act-pair · gpt-3.5-turbo

references to subjective statements about experiences or evaluations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.67

icum

-0.63

isode

-0.63

bow

-0.62

fold

-0.61

icist

-0.61

joining

-0.61

shock

-0.61

Guard

-0.60

elope

-0.60

POSITIVE LOGITS

NetMessage

0.81

 ALWAYS

0.77

 coincided

0.74

 REALLY

0.71

 disproportionately

0.71

 unpredict

0.68

 unavoid

0.68

 underestimated

0.66

 functionally

0.66

*/(

0.66

Activations Density 0.324%

segments discussing problems, issues, or critiques

references to subjective statements about experiences or evaluations

No Comments

No Known Activations