INDEX

Explanations

references to communication attempts or responses

oai_token-act-pair · gpt-3.5-turbo

references to requests for comments or responses from individuals or organizations

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

sed

-0.73

orsche

-0.71

edes

-0.68

 joints

-0.66

 bonding

-0.64

erva

-0.64

unts

-0.63

steen

-0.61

 commanding

-0.61

 valves

-0.61

POSITIVE LOGITS

 Coverage

1.06

 reporter

0.88

 Editorial

0.86

 interview

0.84

 reporters

0.83

 editorial

0.83

 coverage

0.82

 Inqu

0.82

 Newsp

0.82

 contacted

0.81

Activations Density 0.700%

references to communication attempts or responses

references to requests for comments or responses from individuals or organizations

No Comments

No Known Activations