INDEX

Explanations

adjectives describing movement or progress

oai_token-act-pair · gpt-3.5-turbo

frequent punctuation or delimiters in text, particularly commas

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

reprene

-0.87

itarian

-0.85

iless

-0.79

izen

-0.76

izoph

-0.74

onym

-0.74

ictionary

-0.72

ivist

-0.70

urat

-0.69

scribe

-0.69

POSITIVE LOGITS

 scoring

1.19

 averaging

1.17

 finishing

1.11

 albeit

1.05

scoring

0.98

 opting

0.97

 hitting

0.97

 earning

0.97

 completing

0.96

 totaling

0.96

Activations Density 0.237%

adjectives describing movement or progress

frequent punctuation or delimiters in text, particularly commas

No Comments

No Known Activations