INDEX

Explanations

phrases related to specific brands or entities

oai_token-act-pair · gpt-3.5-turbo

names of organizations and words associated with them

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

 stripes

-0.66

 promise

-0.64

 remission

-0.62

ivas

-0.62

 driveway

-0.61

culosis

-0.60

 recess

-0.60

 resolution

-0.59

 Viking

-0.58

 deposition

-0.57

POSITIVE LOGITS

alez

1.01

ener

1.00

ofi

0.93

erent

0.92

orno

0.92

reet

0.88

riger

0.85

endium

0.84

ardless

0.83

ancies

0.83

Activations Density 0.096%

phrases related to specific brands or entities

names of organizations and words associated with them

No Comments

No Known Activations