INDEX

Explanations

locations or settings where events occur

oai_token-act-pair · gpt-3.5-turbo

references to the scene of an incident or event

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thood

-0.99

raltar

-0.82

atever

-0.77

 Seym

-0.76

berman

-0.74

 barley

-0.68

iago

-0.68

matically

-0.66

glomer

-0.65

haps

-0.65

POSITIVE LOGITS

ewitness

0.79

 Scene

0.77

 scene

0.75

Dialogue

0.75

EMS

0.73

 Reconstruction

0.72

 unfold

0.71

 location

0.70

scene

0.70

 site

0.69

Activations Density 0.018%

locations or settings where events occur

references to the scene of an incident or event

No Comments

No Known Activations