INDEX

Explanations

mentions of families

oai_token-act-pair · gpt-3.5-turbo

references to families 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Downloadha

-0.72

 Flavoring

-0.66

iasis

-0.65

oker

-0.64

 Prom

-0.62

umbn

-0.62

igo

-0.60

zeb

-0.59

 Nero

-0.59

ococ

-0.59

POSITIVE LOGITS

chool

1.13

folk

1.04

hetical

0.83

creen

0.77

heses

0.75

 reun

0.75

 bonded

0.74

archs

0.74

hips

0.73

members

0.72

Activations Density 0.024%

mentions of families

references to families in various contexts

No Comments

No Known Activations