INDEX

Explanations

adjectives describing a degree or extent

oai_token-act-pair · gpt-3.5-turbo

instances of the word "rather" 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

elsen

-1.00

ppo

-0.80

ruary

-0.76

ocaust

-0.76

amba

-0.75

illary

-0.73

mberg

-0.72

wana

-0.71

ahu

-0.69

DD

-0.69

POSITIVE LOGITS

 amusing

0.89

 inconvenient

0.85

 unimagin

0.83

 unpleasant

0.82

 pricey

0.80

 awkward

0.80

 incons

0.77

 complicated

0.76

 unusual

0.76

 harmless

0.76

Activations Density 0.016%

adjectives describing a degree or extent

instances of the word "rather" in various contexts

No Comments

No Known Activations