INDEX

Explanations

statements or quotes made by individuals

oai_token-act-pair · gpt-3.5-turbo

statements made by individuals, particularly those implying reported speech or claims

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

JV

-0.74

ctors

-0.73

 Sabha

-0.63

OTAL

-0.63

MJ

-0.63

 Jackets

-0.61

vg

-0.61

quin

-0.61

Osc

-0.60

Mos

-0.59

POSITIVE LOGITS

 repeatedly

0.99

 since

0.89

avering

0.88

 unequivocally

0.84

 contingency

0.79

 intentions

0.77

 numerous

0.77

 reluctance

0.74

interpret

0.72

 intention

0.71

Activations Density 0.187%

statements or quotes made by individuals

statements made by individuals, particularly those implying reported speech or claims

No Comments

No Known Activations