INDEX

Explanations

programming-related terms and syntax

oai_token-act-pair · gpt-3.5-turbo

sequences of unique symbols or formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Brotherhood

-0.98

 Replay

-0.92

 Housing

-0.88

 promotional

-0.88

 rotating

-0.88

 Conc

-0.87

 Shelter

-0.87

 Personal

-0.86

 Consumer

-0.86

 Community

-0.86

POSITIVE LOGITS

cit

1.54

nl

1.51

eu

1.50

rh

1.46

kr

1.46

mad

1.44

nu

1.42

sg

1.42

dan

1.42

sat

1.41

Activations Density 0.278%

programming-related terms and syntax

sequences of unique symbols or formatting

No Comments

No Known Activations