INDEX

Explanations

phrases related to evaluating or assessing someone's performance

oai_token-act-pair · gpt-3.5-turbo

references to "performance" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

yg

-0.80

rir

-0.78

oslov

-0.76

vy

-0.76

sonian

-0.76

cot

-0.75

cott

-0.73

ship

-0.72

yu

-0.71

ski

-0.70

POSITIVE LOGITS

 enhancement

0.91

enh

0.85

 enhancing

0.85

 evaluations

0.83

 appraisal

0.83

istics

0.82

imony

0.80

 evaluation

0.74

rating

0.73

 performances

0.73

Activations Density 0.028%

phrases related to evaluating or assessing someone's performance

references to "performance" in various contexts

No Comments

No Known Activations