INDEX

Explanations

phrases related to being harassed or assaulted

oai_token-act-pair · gpt-3.5-turbo

words related to "assessing" or "trespassing."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

rame

-0.72

VID

-0.72

 resurg

-0.68

 pept

-0.68

ricular

-0.67

td

-0.67

umbo

-0.67

express

-0.67

ãĤ¨

-0.66

circ

-0.65

POSITIVE LOGITS

assed

1.09

assing

0.87

chnology

0.82

asses

0.80

assy

0.74

mble

0.74

byss

0.72

retty

0.72

ignty

0.71

asant

0.71

Activations Density 0.021%

phrases related to being harassed or assaulted

words related to "assessing" or "trespassing."

No Comments

No Known Activations