INDEX

Explanations

phrases related to casual conversation and social interactions

oai_token-act-pair · gpt-3.5-turbo

conversational expressions and interjections

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

sequently

-0.66

ourses

-0.66

-0.65

ourse

-0.64

ilst

-0.64

avering

-0.63

etermined

-0.63

egu

-0.62

sufficient

-0.62

POSITIVE LOGITS

 freaking

0.96

 fucking

0.94

 goddamn

0.94

 crappy

0.94

 damn

0.92

 shitty

0.92

 nerds

0.92

 kidding

0.92

 dudes

0.90

 crap

0.89

Activations Density 1.502%

phrases related to casual conversation and social interactions

conversational expressions and interjections

No Comments

No Known Activations