INDEX

Explanations

objects being described in detail

oai_token-act-pair · gpt-3.5-turbo

phrases that describe items accompanied by the word "with."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

thren

-0.74

ights

-0.70

hack

-0.70

borgh

-0.67

ati

-0.66

Asia

-0.63

cemic

-0.63

Leaks

-0.63

phrine

-0.63

iance

-0.63

POSITIVE LOGITS

stood

1.53

 regard

1.38

 regards

1.31

drawn

1.17

 respect

1.14

standing

1.06

 impunity

1.05

draw

1.05

holding

0.87

 whom

0.78

Activations Density 0.174%

objects being described in detail

phrases that describe items accompanied by the word "with."

No Comments

No Known Activations