INDEX

Explanations

details of personal experiences, especially involving interactions with other people

oai_token-act-pair · gpt-3.5-turbo

nondescript yet emotionally charged dialogue

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

selves

-0.75

moil

-0.71

 collectively

-0.71

 unison

-0.69

 respectively

-0.66

ielding

-0.64

iren

-0.61

 respective

-0.59

 constituted

-0.59

hub

-0.58

POSITIVE LOGITS

 himself

1.50

 Himself

1.06

me

0.98

his

0.95

us

0.91

 ..."

0.81

 âĢ¦"

0.79

 ours

0.76

 somet

0.74

 fuckin

0.73

Activations Density 0.893%

details of personal experiences, especially involving interactions with other people

nondescript yet emotionally charged dialogue

No Comments

No Known Activations