INDEX

Explanations

mentions of branding or labeling

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "bl" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Gund

-0.76

HER

-0.72

reon

-0.68

LER

-0.66

 Simulator

-0.66

 Democr

-0.64

ORGE

-0.62

roit

-0.61

aeda

-0.61

 Engel

-0.61

POSITIVE LOGITS

anca

1.17

ossom

1.14

anco

1.09

umenthal

1.08

anche

1.07

adder

1.07

estone

0.99

adders

0.98

acks

0.97

anches

0.95

Activations Density 0.022%

mentions of branding or labeling

occurrences of the word "bl" in various contexts

No Comments

No Known Activations