INDEX

Explanations

academic or professional titles followed by a person's name

oai_token-act-pair · gpt-3.5-turbo

references to academic or professional associates and their roles

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

stakes

-0.85

Ö¼

-0.84

enegger

-0.82

=-=-=-=-=-=-=-=-

-0.82

CRIP

-0.79

AAF

-0.79

gm

-0.77

atility

-0.77

raltar

-0.77

cale

-0.76

POSITIVE LOGITS

 dean

0.88

 associate

0.83

 newsp

0.80

iate

0.75

lly

0.74

lies

0.73

ociate

0.72

 professor

0.72

 Cind

0.68

rete

0.66

Activations Density 0.016%

academic or professional titles followed by a person's name

references to academic or professional associates and their roles

No Comments

No Known Activations