INDEX

Explanations

terms related to catastrophic events or breakdowns

oai_token-act-pair · gpt-3.5-turbo

instances of the word "collapse" and its various forms

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

qua

-0.80

friends

-0.77

ju

-0.72

lean

-0.70

ledge

-0.69

Choice

-0.69

cil

-0.69

prim

-0.69

etch

-0.69

Ã±a

-0.68

POSITIVE LOGITS

 inertia

0.82

ateral

0.80

 containment

0.79

ulence

0.79

 collapse

0.79

opian

0.78

ibility

0.77

 contag

0.76

icter

0.73

 tremend

0.73

Activations Density 0.030%

terms related to catastrophic events or breakdowns

instances of the word "collapse" and its various forms

No Comments

No Known Activations