INDEX

Explanations

names related to political figures and political events

oai_token-act-pair · gpt-3.5-turbo

specific names or technical details related to individuals or entities

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

 suspic

-0.76

 whistle

-0.73

 rooting

-0.73

PDATE

-0.72

 predictor

-0.71

 millenn

-0.70

 enthusi

-0.66

METHOD

-0.66

 bearer

-0.65

ĸļ

-0.65

POSITIVE LOGITS

aya

0.98

ema

0.80

 County

0.78

arij

0.77

eta

0.76

aii

0.76

ayan

0.75

zyk

0.75

deen

0.75

gui

0.74

Activations Density 0.379%

names related to political figures and political events

specific names or technical details related to individuals or entities

No Comments

No Known Activations