INDEX

Explanations

options or choices discussed in a text

oai_token-act-pair · gpt-3.5-turbo

mentions of options or alternatives

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

urst

-0.76

mind

-0.75

soever

-0.75

hemat

-0.73

tub

-0.72

grave

-0.71

rollers

-0.69

ritic

-0.69

itizens

-0.67

ãĤ·ãĥ£

-0.65

POSITIVE LOGITS

 options

1.00

 option

0.89

atives

0.86

finder

0.84

 choices

0.77

 Option

0.74

Option

0.73

 choice

0.71

izons

0.71

rison

0.70

Activations Density 0.027%

options or choices discussed in a text

mentions of options or alternatives

No Comments

No Known Activations