INDEX

Explanations

references to literacy and literature

oai_token-act-pair · gpt-3.5-turbo

references to literacy and its various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Sands

-0.73

 Parenthood

-0.69

swer

-0.69

Ĥª

-0.65

cffffcc

-0.62

ktop

-0.61

IELD

-0.60

rontal

-0.60

ressing

-0.59

 palms

-0.59

POSITIVE LOGITS

atures

1.28

acy

1.10

acies

1.08

uania

1.04

ature

0.96

umen

0.91

 liter

0.88

ocity

0.85

ging

0.85

liter

0.84

Activations Density 0.020%

references to literacy and literature

references to literacy and its various forms

No Comments

No Known Activations