INDEX

Explanations

phrases describing physical actions involving objects

oai_token-act-pair · gpt-3.5-turbo

occurrences of the article "a"

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

Own

-0.83

Sources

-0.83

Rules

-0.83

Events

-0.79

Discuss

-0.77

tests

-0.76

evidence

-0.74

Iss

-0.74

Edit

-0.73

States

-0.73

POSITIVE LOGITS

 handful

1.14

 bunch

1.06

rouse

0.99

 broom

0.98

 breeze

0.98

 knife

0.96

 flurry

0.95

 tray

0.94

few

0.93

 multitude

0.93

Activations Density 0.472%

phrases describing physical actions involving objects

occurrences of the article "a"

No Comments

No Known Activations