INDEX

Explanations

mentions of individuals' names or identifiers

oai_token-act-pair · gpt-3.5-turbo

repetitions of the name "Biden" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

pmwiki

-0.72

 Canadians

-0.67

mable

-0.66

 uncontrolled

-0.66

 exha

-0.65

 weeds

-0.63

thora

-0.62

 Rita

-0.62

 semif

-0.59

 vanquished

-0.59

POSITIVE LOGITS

iden

1.68

unci

0.88

furt

0.82

zen

0.79

emy

0.79

ovo

0.79

acity

0.79

ovic

0.78

isen

0.78

nen

0.78

Activations Density 0.010%

mentions of individuals' names or identifiers

repetitions of the name "Biden" and its variations

No Comments

No Known Activations