INDEX

Explanations

phrases related to specific actions or events happening

oai_token-act-pair · gpt-3.5-turbo

isolated clauses that provide context or details in a sentence

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

ety

-0.70

¬¼

-0.70

raved

-0.69

iple

-0.64

rite

-0.63

rio

-0.63

ITE

-0.61

ocl

-0.61

scription

-0.59

 Founding

-0.59

POSITIVE LOGITS

 whereas

1.13

 thereby

1.09

 respectively

1.06

 regardless

1.03

 preferably

0.97

 resulting

0.95

 namely

0.94

etc

0.94

 although

0.92

 depending

0.92

Activations Density 0.810%

phrases related to specific actions or events happening

isolated clauses that provide context or details in a sentence

No Comments

No Known Activations