INDEX

Explanations

mentions of a specific individual's name in a negative context

oai_token-act-pair · gpt-3.5-turbo

words related to an individual's name or identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

schild

-0.78

space

-0.76

enegger

-0.74

line

-0.72

starter

-0.69

sheet

-0.69

tal

-0.69

birds

-0.66

lings

-0.65

hawk

-0.64

POSITIVE LOGITS

Ã±

0.94

edia

0.90

pered

0.89

cess

0.88

uthor

0.84

pload

0.83

odcast

0.81

pa

0.81

resa

0.80

apa

0.80

Activations Density 0.011%

mentions of a specific individual's name in a negative context

words related to an individual's name or identity

No Comments

No Known Activations