INDEX

Explanations

instances of the word "Wal" with varying strengths of activation

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Wal" likely related to Wal-Mart

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

IBLE

-0.80

 Carbuncle

-0.79

nces

-0.73

 Dragonbound

-0.73

 Butterfly

-0.73

 Darkness

-0.70

éĹĺ

-0.66

ities

-0.65

 Chomsky

-0.64

OVA

-0.64

POSITIVE LOGITS

nut

1.10

nuts

1.05

vey

0.99

cott

0.97

ley

0.85

leys

0.84

nesday

0.83

stad

0.82

cohol

0.82

adr

0.82

Activations Density 0.010%

instances of the word "Wal" with varying strengths of activation

occurrences of the word "Wal" likely related to Wal-Mart

No Comments

No Known Activations