INDEX

Explanations

mentions of the word "auto" or related terms like "autoantibodies"

oai_token-act-pair · gpt-3.5-turbo

references to automobiles and automotive-related terms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ĸļ

-0.98

enance

-0.85

hips

-0.81

 GOODMAN

-0.79

ATER

-0.78

ewski

-0.77

soever

-0.77

 Beir

-0.75

redients

-0.74

REAM

-0.74

POSITIVE LOGITS

immune

1.02

cephal

0.97

 autos

0.89

actively

0.85

 auto

0.82

 accident

0.78

 compr

0.77

incre

0.77

 bailout

0.75

 accidents

0.74

Activations Density 0.008%

mentions of the word "auto" or related terms like "autoantibodies"

references to automobiles and automotive-related terms

No Comments

No Known Activations