INDEX

Explanations

information about where someone worked, their career, or their job transitions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the phrase "worked in" followed by various fields or industries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

casters

-0.83

fd

-0.71

dule

-0.70

Results

-0.69

[_

-0.69

 attm

-0.69

iframe

-0.69

day

-0.68

selves

-0.68

soever

-0.68

POSITIVE LOGITS

 academia

1.33

 obscurity

1.08

 lieu

1.07

 exile

1.06

 conjunction

1.00

 captivity

0.98

patient

0.94

 limbo

0.94

 vain

0.92

 relation

0.91

Activations Density 0.193%

information about where someone worked, their career, or their job transitions

occurrences of the phrase "worked in" followed by various fields or industries

No Comments

No Known Activations