INDEX

Explanations

verbs related to movement through or across a space

oai_token-act-pair · gpt-3.5-turbo

words related to abstract or pervasive concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

bay

-0.71

 tilt

-0.68

 captives

-0.66

 surn

-0.66

 jobs

-0.63

 Directors

-0.63

 partName

-0.63

 filibuster

-0.63

 depos

-0.63

 Bash

-0.62

POSITIVE LOGITS

agher

1.07

abil

1.04

SPONSORED

1.00

resent

0.98

ibel

0.94

assing

0.93

ibe

0.91

odied

0.91

coe

0.89

cend

0.86

Activations Density 0.037%

verbs related to movement through or across a space

words related to abstract or pervasive concepts

No Comments

No Known Activations