INDEX

Explanations

mentions of specific names or titles related to entertainment media

oai_token-act-pair · gpt-3.5-turbo

mentions of specific television shows and notable characters associated with them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ĺħ

-0.82

xual

-0.79

xtap

-0.74

antha

-0.73

ozo

-0.73

eering

-0.73

quez

-0.72

iasis

-0.71

uration

-0.69

anchester

-0.68

POSITIVE LOGITS

leneck

0.85

gets

0.83

iesel

0.75

EEK

0.71

lev

0.70

hiba

0.68

ynski

0.68

wana

0.67

JB

0.65

YL

0.65

Activations Density 0.093%

mentions of specific names or titles related to entertainment media

mentions of specific television shows and notable characters associated with them

No Comments

No Known Activations