INDEX

Explanations

numerical rankings and positions

oai_token-act-pair · gpt-3.5-turbo

rankings or positions in competitions or events

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

 brim

-0.68

ROR

-0.60

Rules

-0.58

 therape

-0.57

CRE

-0.56

 Inquiry

-0.56

olutions

-0.56

Paper

-0.55

 Substance

-0.55

Tang

-0.55

POSITIVE LOGITS

 baseman

1.01

arily

0.93

hand

0.87

ority

0.80

onyms

0.79

isl

0.77

ranked

0.77

lane

0.75

oths

0.72

eter

0.72

Activations Density 0.071%

numerical rankings and positions

rankings or positions in competitions or events

No Comments

No Known Activations