INDEX

Explanations

names of individuals or fictional characters

oai_token-act-pair · gpt-3.5-turbo

words related to scientific or biological classifications, particularly names of species or genera

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

ishers

-0.82

sheet

-0.82

ry

-0.75

ered

-0.75

ried

-0.75

istically

-0.74

ership

-0.73

sie

-0.72

erick

-0.71

ishly

-0.71

POSITIVE LOGITS

aurus

1.21

ocial

1.01

hift

0.97

CRIP

0.96

ource

0.94

peed

0.93

ilon

0.88

henko

0.87

ktop

0.87

cale

0.85

Activations Density 0.107%

names of individuals or fictional characters

words related to scientific or biological classifications, particularly names of species or genera

No Comments

No Known Activations