INDEX

Explanations

text snippets related to the name "Abe"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Abe" or references to individuals associated with that name

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

phis

-0.97

neapolis

-0.83

ophical

-0.82

stream

-0.78

imates

-0.77

speak

-0.77

achusetts

-0.75

wise

-0.75

ieth

-0.74

marked

-0.73

POSITIVE LOGITS

zz

0.82

legates

0.77

Ã§a

0.76

zza

0.75

eas

0.72

legate

0.71

ÅŁ

0.71

uge

0.69

FORE

0.69

lde

0.69

Activations Density 0.049%

text snippets related to the name "Abe"

occurrences of the name "Abe" or references to individuals associated with that name

No Comments

No Known Activations