INDEX

Explanations

phrases indicating responsibility or actions of specific individuals or groups

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate accountability or responsibility

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

aukee

-0.73

rique

-0.70

ilial

-0.70

ricane

-0.70

anus

-0.69

onut

-0.67

poon

-0.67

ruary

-0.65

avorite

-0.64

 basil

-0.64

POSITIVE LOGITS

...]

0.72

offs

0.62

ainer

0.61

 theoret

0.60

erous

0.59

aders

0.57

urers

0.57

uary

0.57

 attm

0.57

ography

0.57

Activations Density 0.015%

phrases indicating responsibility or actions of specific individuals or groups

phrases that indicate accountability or responsibility

No Comments

No Known Activations