INDEX

Explanations

the names of theaters or venues

oai_token-act-pair · gpt-3.5-turbo

mentions of specific theaters or venues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

£ı

-0.82

vironment

-0.78

rint

-0.77

istries

-0.77

aunder

-0.74

ulkan

-0.71

itor

-0.70

achev

-0.70

arah

-0.69

itude

-0.68

POSITIVE LOGITS

wright

0.97

 Workshop

0.90

writers

0.84

writer

0.83

 trou

0.82

wr

0.82

 Theatre

0.81

 marqu

0.79

plays

0.77

Pub

0.73

Activations Density 0.030%

the names of theaters or venues

mentions of specific theaters or venues

No Comments

No Known Activations