INDEX

Explanations

words or phrases related to being filled or infested with something negative or problematic

oai_token-act-pair · gpt-3.5-turbo

terms related to issues, problems, or negative conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ift

-0.78

mpeg

-0.72

 sidx

-0.70

pressed

-0.66

ifted

-0.65

uber

-0.65

hal

-0.63

cel

-0.61

friend

-0.61

cell

-0.59

POSITIVE LOGITS

 plagued

0.94

 littered

0.82

 rife

0.81

 riddled

0.74

DOS

0.71

 Mania

0.69

entimes

0.68

riad

0.67

rodu

0.67

slaught

0.65

Activations Density 0.022%

words or phrases related to being filled or infested with something negative or problematic

terms related to issues, problems, or negative conditions

No Comments

No Known Activations