INDEX

Explanations

proper nouns, possibly related to controversies or conflicts

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names and terms related to people or entities in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

esthetic

-0.98

ily

-0.83

esthesia

-0.82

meric

-0.80

eco

-0.75

ijk

-0.73

iland

-0.73

erm

-0.72

ilic

-0.72

java

-0.72

POSITIVE LOGITS

aneous

0.96

 Cumber

0.84

 Lauder

0.81

hyde

0.80

aire

0.77

batch

0.76

ative

0.75

ror

0.70

FORE

0.70

aneously

0.69

Activations Density 0.190%

proper nouns, possibly related to controversies or conflicts

mentions of specific names and terms related to people or entities in context

No Comments

No Known Activations