INDEX

Explanations

names and titles of officials or representatives

oai_token-act-pair · gpt-3.5-turbo

phrases indicating roles or positions of spokespersons

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

utterstock

-0.83

eat

-0.72

avascript

-0.68

reci

-0.68

oor

-0.66

secure

-0.64

VALUE

-0.64

ems

-0.63

floor

-0.62

stakes

-0.62

POSITIVE LOGITS

 prosecuting

0.76

mbuds

0.75

 Cause

0.74

 Guer

0.74

 Sent

0.73

 STATS

0.69

 Respond

0.67

 interven

0.67

 defending

0.66

 Coun

0.66

Activations Density 0.063%

names and titles of officials or representatives

phrases indicating roles or positions of spokespersons

No Comments

No Known Activations