INDEX

Explanations

names and terms related to political figures or events

oai_token-act-pair · gpt-3.5-turbo

terms related to identity or identification, particularly in a political or social context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Seattle

-0.74

TPP

-0.73

trace

-0.72

strings

-0.70

fecture

-0.70

erest

-0.70

esters

-0.70

gling

-0.69

itures

-0.68

xon

-0.68

POSITIVE LOGITS

 Hussain

1.52

 Sharif

1.51

uddin

1.50

ullah

1.47

 Hassan

1.42

 Ahmad

1.42

 Abdul

1.41

Abu

1.40

ibn

1.40

Ali

1.40

Activations Density 0.156%

names and terms related to political figures or events

terms related to identity or identification, particularly in a political or social context

No Comments

No Known Activations