INDEX

Explanations

expressions related to failure or negative outcomes

oai_token-act-pair · gpt-3.5-turbo

instances of the word "fo" and other related terms suggestive of failure or administrative actions

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

 Lumpur

-0.66

 Sector

-0.66

uyomi

-0.66

 Poster

-0.62

 Norn

-0.61

Downloadha

-0.60

 warr

-0.59

owship

-0.59

é¾įå¥ĳå£«

-0.59

XY

-0.59

POSITIVE LOGITS

eton

0.82

eto

0.81

emen

0.81

isted

0.78

oche

0.77

oing

0.77

ogs

0.77

umbers

0.76

cludes

0.75

amy

0.75

Activations Density 0.011%

expressions related to failure or negative outcomes

instances of the word "fo" and other related terms suggestive of failure or administrative actions

No Comments

No Known Activations