INDEX

Explanations

words related to scientific, technical, or analytical contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the end of sequences or document boundaries

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Defenders

-0.83

 Companion

-0.82

 Mellon

-0.82

 Immunity

-0.74

 Elves

-0.72

 Healer

-0.72

 Balanced

-0.71

 Investigator

-0.69

 Hale

-0.69

 Standards

-0.69

POSITIVE LOGITS

ve

0.99

rill

0.96

vern

0.95

gey

0.95

vel

0.94

vey

0.92

vered

0.91

reating

0.91

oming

0.91

reprene

0.89

Activations Density 0.161%

words related to scientific, technical, or analytical contexts

instances of the end of sequences or document boundaries

No Comments

No Known Activations