INDEX

Explanations

verbs indicating someone speaking or providing information

oai_token-act-pair · gpt-3.5-turbo

instances of quotation marks or reported speech

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

tumblr

-0.77

LET

-0.72

arest

-0.70

illions

-0.70

Holy

-0.69

isable

-0.69

respective

-0.68

pe

-0.66

Pages

-0.66

TABLE

-0.65

POSITIVE LOGITS

 bluntly

0.83

 sarcast

0.82

 anecd

0.81

 afterward

0.78

 goodbye

0.72

heit

0.70

 emphatically

0.70

essler

0.69

KR

0.69

doms

0.68

Activations Density 0.175%

verbs indicating someone speaking or providing information

instances of quotation marks or reported speech

No Comments

No Known Activations