INDEX

Explanations

names or terms related to a particular geographical location

oai_token-act-pair · gpt-3.5-turbo

occurrences of the sequence "utt" in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

isSpecialOrderable

-0.80

ã

-0.73

 corros

-0.69

 retri

-0.65

 dissolution

-0.61

bri

-0.59

 clerks

-0.59

 exha

-0.57

tyr

-0.57

 streamed

-0.57

POSITIVE LOGITS

erella

1.16

erers

0.95

gart

0.90

ilton

0.86

elta

0.84

erer

0.84

itsu

0.83

iness

0.82

iest

0.80

elson

0.80

Activations Density 0.031%

names or terms related to a particular geographical location

occurrences of the sequence "utt" in the text

No Comments

No Known Activations