INDEX

Explanations

phrases containing the letters "gh" in specific positions within words

oai_token-act-pair · gpt-3.5-turbo

variations of the substring "gh"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Bots

-0.77

 satell

-0.75

nesday

-0.68

 closest

-0.66

 Faust

-0.66

 cort

-0.65

IAL

-0.65

 deleg

-0.64

 Draper

-0.63

 indo

-0.60

POSITIVE LOGITS

ttp

1.09

gh

0.97

ouls

0.94

mt

0.92

ats

0.90

orns

0.88

ild

0.88

orst

0.86

awk

0.84

ij

0.84

Activations Density 0.008%

phrases containing the letters "gh" in specific positions within words

variations of the substring "gh"

No Comments

No Known Activations