INDEX

Explanations

references to documentation or instructions

oai_token-act-pair · gpt-3.5-turbo

references to documentation 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 @ 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

awar

-0.80

otin

-0.78

olean

-0.76

cker

-0.71

cot

-0.71

cffffcc

-0.69

cffff

-0.68

zanne

-0.68

ideshow

-0.65

nie

-0.65

POSITIVE LOGITS

 documentation

1.08

 Documentation

0.84

 documenting

0.84

 detailing

0.79

herty

0.79

 docs

0.74

 markup

0.74

documented

0.72

docs

0.72

arily

0.71

Activations Density 0.018%

references to documentation or instructions

references to documentation in various contexts

No Comments

No Known Activations