INDEX

Explanations

statements where a case is being made or argued for

oai_token-act-pair · gpt-3.5-turbo

arguments or claims being made

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

 Seym

-0.80

ummer

-0.72

attery

-0.69

onder

-0.69

elta

-0.65

semb

-0.64

kered

-0.62

umber

-0.62

ombs

-0.61

 Pixie

-0.61

POSITIVE LOGITS

 against

0.82

cases

0.80

Against

0.79

 convinc

0.78

case

0.73

why

0.72

 persuasive

0.72

 compelling

0.71

 convincing

0.70

.","

0.70

Activations Density 0.032%

statements where a case is being made or argued for

arguments or claims being made

No Comments

No Known Activations