INDEX

Explanations

rankings or positions

oai_token-act-pair · gpt-3.5-turbo

references to rankings across various contexts

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

 Leilan

-0.77

Tik

-0.77

vous

-0.76

icer

-0.68

alone

-0.65

 Samar

-0.65

romy

-0.63

fitting

-0.61

anti

-0.61

rial

-0.61

POSITIVE LOGITS

 rankings

1.09

 ranking

0.96

 Rankings

0.91

 Ranking

0.80

Rank

0.80

ikuman

0.77

elist

0.76

 algorithm

0.75

 contenders

0.75

 criteria

0.73

Activations Density 0.020%

rankings or positions

references to rankings across various contexts

No Comments

No Known Activations