INDEX

Explanations

genres and subgenres of music

oai_token-act-pair · gpt-3.5-turbo

references to different genres of rock and metal music

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

pread

-0.75

 Volunte

-0.74

vre

-0.67

urion

-0.67

cius

-0.67

Kis

-0.66

EStream

-0.66

 Cheong

-0.66

 Kers

-0.65

 clot

-0.65

POSITIVE LOGITS

 genres

1.02

 genre

0.99

core

0.96

 powerhouse

0.91

 revival

0.90

 punk

0.90

 lyrics

0.89

 music

0.89

punk

0.89

 legend

0.89

Activations Density 0.097%

genres and subgenres of music

references to different genres of rock and metal music

No Comments

No Known Activations