INDEX

Explanations

mentions of the name "Gerry" at varying activations

oai_token-act-pair · gpt-3.5-turbo

references to the word "berry" and its variations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

agos

-0.90

isting

-0.76

ahime

-0.75

aepernick

-0.75

iesta

-0.75

agonist

-0.75

icago

-0.75

awar

-0.74

ouch

-0.74

anooga

-0.73

POSITIVE LOGITS

mand

1.05

mite

0.79

erry

0.78

ments

0.77

 Gerry

0.76

mph

0.74

bye

0.73

nda

0.72

llo

0.71

ng

0.70

Activations Density 0.018%

mentions of the name "Gerry" at varying activations

references to the word "berry" and its variations

No Comments

No Known Activations