INDEX

Explanations

words related to hindrance or obstruction

oai_token-act-pair · gpt-3.5-turbo

references to "hind" or related terms, indicating a focus on that specific subject

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ailability

-0.66

iliary

-0.66

ancouver

-0.65

ids

-0.64

itÃ©

-0.64

HRC

-0.59

iott

-0.57

ctica

-0.57

 Waterloo

-0.57

atton

-0.56

POSITIVE LOGITS

ering

1.21

rance

1.02

erers

1.00

ered

0.99

nesses

0.98

sight

0.97

erer

0.94

ern

0.90

vention

0.83

quarters

0.83

Activations Density 0.060%

words related to hindrance or obstruction

references to "hind" or related terms, indicating a focus on that specific subject

No Comments

No Known Activations