INDEX

Explanations

mentions of political figures, particularly senators

oai_token-act-pair · gpt-3.5-turbo

references to senators

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sticky

-0.67

 civilisation

-0.66

tru

-0.64

theless

-0.64

 misunderstanding

-0.64

 managerial

-0.63

 factor

-0.63

 feats

-0.63

 tolerance

-0.61

 underpin

-0.61

POSITIVE LOGITS

iors

1.26

eca

1.14

seless

1.00

essee

0.99

escent

0.99

pai

0.98

esse

0.96

iture

0.95

.,

0.91

itive

0.88

Activations Density 0.018%

mentions of political figures, particularly senators

references to senators

No Comments

No Known Activations