INDEX

Explanations

negative phrases or connotations related to a specific symbol or phrase

oai_token-act-pair · gpt-3.5-turbo

special characters or symbols in text

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

(=

-0.64

<@

-0.63

enta

-0.61

 freaking

-0.59

 artif

-0.59

 sidx

-0.59

 carriage

-0.58

kil

-0.57

ãĥķãĤ¡

-0.57

omorphic

-0.57

POSITIVE LOGITS

requires

0.88

dayName

0.83

feat

0.79

were

0.78

eatures

0.77

include

0.74

than

0.74

while

0.74

dep

0.72

Frames

0.72

Activations Density 0.113%

negative phrases or connotations related to a specific symbol or phrase

special characters or symbols in text

No Comments

No Known Activations