INDEX

Explanations

instances of finger-pointing or blaming between individuals or groups

oai_token-act-pair · gpt-3.5-turbo

terminology related to pointing or indicating action

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

ĻĤ

-0.69

Beta

-0.67

 cryst

-0.66

Bright

-0.65

SEA

-0.64

ãĥĺãĥ©

-0.63

éĸ

-0.63

Fixed

-0.63

sole

-0.63

ELE

-0.63

POSITIVE LOGITS

ingly

1.04

 antics

0.84

 insults

0.82

 humour

0.82

 apolog

0.81

 accusations

0.81

 tactics

0.80

manship

0.80

 prick

0.80

 jokes

0.79

Activations Density 0.351%

instances of finger-pointing or blaming between individuals or groups

terminology related to pointing or indicating action

No Comments

No Known Activations