INDEX

Explanations

information attributed to specific sources

oai_token-act-pair · gpt-3.5-turbo

mentions of sources or references in the text

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

aeper

-0.82

osate

-0.76

TAG

-0.74

ĸļ

-0.72

Ħ¢

-0.68

 Potato

-0.65

eg

-0.64

-0.63

eers

-0.61

 potato

-0.61

POSITIVE LOGITS

 sources

1.04

 informants

0.88

 Sources

0.84

 consulted

0.80

 knowledgeable

0.76

source

0.72

 cited

0.72

ources

0.72

 source

0.72

 briefed

0.71

Activations Density 0.021%

information attributed to specific sources

mentions of sources or references in the text

No Comments

No Known Activations