INDEX

Explanations

adjectives describing the nature or characteristics of actions or situations

oai_token-act-pair · gpt-3.5-turbo

references to limitations and sporadic issues in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EStream

-0.84

iage

-0.82

orks

-0.80

kees

-0.79

onica

-0.77

kay

-0.77

gdala

-0.76

raine

-0.76

olphins

-0.75

deen

-0.75

POSITIVE LOGITS

 predictable

1.12

 riddled

1.09

 reliant

1.08

 unpredictable

1.06

 comprised

1.02

 fragmented

1.02

 characterized

1.01

 dependent

1.00

 inconsistent

1.00

 irreversible

0.98

Activations Density 0.233%

adjectives describing the nature or characteristics of actions or situations

references to limitations and sporadic issues in various contexts

No Comments

No Known Activations