INDEX

Explanations

mentions of press conferences

oai_token-act-pair · gpt-3.5-turbo

mentions of press conferences or press briefings

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

abama

-0.72

 Reconstruction

-0.71

inho

-0.70

thal

-0.69

 Bram

-0.68

 Scotia

-0.63

iHUD

-0.63

ateral

-0.63

[|

-0.61

DAM

-0.61

POSITIVE LOGITS

urized

1.27

conference

1.00

 conference

0.99

 conferences

0.92

ured

0.91

room

0.91

ures

0.88

 corps

0.88

wire

0.85

eval

0.85

Activations Density 0.039%

mentions of press conferences

mentions of press conferences or press briefings

No Comments

No Known Activations