INDEX

Explanations

incidents or events that have occurred

oai_token-act-pair · gpt-3.5-turbo

the occurrence of events or incidents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

atching

-0.79

arij

-0.77

iled

-0.77

ledge

-0.77

step

-0.77

axter

-0.76

zie

-0.75

tan

-0.74

opic

-0.72

itte

-0.72

POSITIVE LOGITS

 occurring

0.91

 occurred

0.89

 undone

0.82

Pause

0.78

TextColor

0.77

[&

0.76

occ

0.76

ĸļ

0.75

cffffcc

0.73

 occurrences

0.72

Activations Density 0.010%

incidents or events that have occurred

the occurrence of events or incidents

No Comments

No Known Activations