INDEX

Explanations

specific formatting cues or markers in an article or text

oai_token-act-pair · gpt-3.5-turbo

indicators of a story or narrative structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MPG

-0.71

 barg

-0.68

 homebrew

-0.65

mbuds

-0.65

 intu

-0.64

 unsuspecting

-0.61

 sails

-0.59

 Compan

-0.57

umenthal

-0.57

 informal

-0.57

POSITIVE LOGITS

ccording

0.74

 Marino

0.74

JUST

0.73

Lua

0.71

Its

0.69

Adding

0.68

ilial

0.67

VERTISEMENT

0.67

MRI

0.66

Job

0.66

Activations Density 0.024%

specific formatting cues or markers in an article or text

indicators of a story or narrative structure

No Comments

No Known Activations