INDEX

Explanations

words related to legal actions and processes

oai_token-act-pair · gpt-3.5-turbo

variations of the word "cue" in different forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

WC

-0.65

 Shards

-0.64

Lay

-0.62

 implants

-0.60

WD

-0.60

Assembly

-0.59

renheit

-0.57

Wan

-0.57

 hump

-0.57

 implant

-0.57

POSITIVE LOGITS

ues

1.07

ued

1.02

hift

0.95

uing

0.93

itionally

0.90

eer

0.89

mble

0.88

eem

0.85

ean

0.85

ilver

0.84

Activations Density 0.012%

words related to legal actions and processes

variations of the word "cue" in different forms

No Comments

No Known Activations