INDEX

Explanations

phrases related to remote locations or control

oai_token-act-pair · gpt-3.5-turbo

terms related to remote operations or controls

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

ICAN

-0.85

OIL

-0.84

ione

-0.78

hetti

-0.76

utenberg

-0.76

 Machina

-0.74

rael

-0.73

trump

-0.73

ÏĦ

-0.72

leck

-0.72

POSITIVE LOGITS

 sensing

1.03

 controlled

0.81

 viewing

0.79

 valley

0.77

 deton

0.76

 control

0.74

 remote

0.72

 outpost

0.72

controlled

0.71

 detachment

0.71

Activations Density 0.026%

phrases related to remote locations or control

terms related to remote operations or controls

No Comments

No Known Activations