INDEX

Explanations

references to issues or experiences specific to women

oai_token-act-pair · gpt-3.5-turbo

repetitions of the phrase "in [location or context]."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

LOG

-0.74

Completed

-0.69

GROUND

-0.68

CVE

-0.67

CLASSIFIED

-0.67

FIG

-0.66

Iterator

-0.66

Users

-0.65

 incumb

-0.65

 sensations

-0.65

POSITIVE LOGITS

 accordance

1.12

ordinate

1.06

 favor

1.00

 vitro

0.98

 vain

0.97

 lieu

0.97

 relation

0.97

efficiency

0.97

organic

0.94

animate

0.94

Activations Density 0.307%

references to issues or experiences specific to women

repetitions of the phrase "in [location or context]."

No Comments

No Known Activations