INDEX

Explanations

descriptions of physical objects

oai_token-act-pair · gpt-3.5-turbo

phrases indicating perception or realization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Bere

-0.65

 Addiction

-0.64

 renaissance

-0.64

 maternity

-0.62

 Champions

-0.61

 truce

-0.61

 sustainability

-0.61

 Domestic

-0.60

 kindred

-0.59

 Leadership

-0.59

POSITIVE LOGITS

 guessed

1.12

 guesses

1.06

 guess

1.05

 guessing

1.00

 inspecting

0.94

 scanned

0.91

 inspection

0.89

 infer

0.88

 zoom

0.87

 scan

0.86

Activations Density 0.955%

descriptions of physical objects

phrases indicating perception or realization

No Comments

No Known Activations