INDEX

Explanations

references to rankings or positions, especially in a sports context

oai_token-act-pair · gpt-3.5-turbo

ordinal rankings or positions in a competitive context

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

gypt

-0.76

 herds

-0.74

 inver

-0.67

lag

-0.66

 enthusi

-0.66

 buggy

-0.66

 bunny

-0.65

ande

-0.64

ãĥ¼ãĥĨ

-0.63

bir

-0.63

POSITIVE LOGITS

CLASSIFIED

0.89

McC

0.78

DIV

0.78

eous

0.76

Hig

0.74

gov

0.72

 Ranking

0.70

Ops

0.69

ificant

0.68

0.67

Activations Density 0.030%

references to rankings or positions, especially in a sports context

ordinal rankings or positions in a competitive context

No Comments

No Known Activations