INDEX

Explanations

words related to job performance and evaluations

oai_token-act-pair · gpt-3.5-turbo

references to performance metrics or assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

oslov

-0.82

ski

-0.79

yg

-0.77

ship

-0.75

rir

-0.75

yu

-0.74

sonian

-0.72

cott

-0.71

vy

-0.71

raft

-0.70

POSITIVE LOGITS

 enhancement

0.96

 enhancing

0.94

enh

0.93

 appraisal

0.91

 evaluations

0.90

 evaluation

0.85

Enh

0.76

 improvement

0.75

rated

0.74

 optimization

0.73

Activations Density 0.033%

words related to job performance and evaluations

references to performance metrics or assessments

No Comments

No Known Activations