INDEX

Explanations

phrases related to observations or statements about specific things

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the importance or significance of a "thing" or concept

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

geon

-0.76

fort

-0.75

rift

-0.74

raph

-0.74

MAP

-0.73

renheit

-0.73

=-=-

-0.71

NAS

-0.66

rn

-0.65

msg

-0.64

POSITIVE LOGITS

 happ

0.81

 happen

0.81

 happening

0.80

cov

0.73

 happened

0.68

fry

0.65

 separates

0.64

 happens

0.63

det

0.62

 missing

0.62

Activations Density 0.133%

phrases related to observations or statements about specific things

phrases emphasizing the importance or significance of a "thing" or concept

No Comments

No Known Activations